Model selection for robust learning of mutational signatures using Negative Binomial non-negative matrix factorization

The spectrum of mutations in a collection of cancer genomes can be described by a mixture of a few mutational signatures. The mutational signatures can be found using non-negative matrix factorization (NMF). To extract the mutational signatures we have to assume a distribution for the observed mutational counts and a number of mutational signatures. In most applications, the mutational counts are assumed to be Poisson distributed, but they are often overdispersed, and thus the Negative Binomial distribution is more appropriate. We demonstrate using a simulation study that Negative Binomial NMF requires fewer signatures than Poisson NMF to fit the data and we propose a Negative Binomial NMF with a patient specific overdispersion parameter to capture the variation across patients. We also introduce a robust model selection procedure inspired by cross-validation to determine the number of signatures. Furthermore we study the influence of the distributional assumption in relation to two classical model selection procedures: the Akaike information criterion (AIC) and the Bayesian information criterion (BIC). In the presence of overdispersion we show that our model selection procedure is more robust at determining the correct number of signatures than state-of-the-art methods, which are overestimating the number of signatures. We apply our proposed analysis on a wide range of simulated data and on a data set from breast cancer patients. The code for our algorithms and analysis is available in the R package SigMoS and can be found at https://github.com/MartaPelizzola/SigMoS.